- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[Communications in Computer and Information Science] Advances in Signal Processing and Intelligent Recognition Systems Volume 968 (4th International Symposium SIRS 2018, Bangalore, India, September 19–22, 2018, Revised Selected Papers) || Pre-processed Hyperspectral Image Analysis Using Tensor Decomposition Techniques
摘要： Hyperspectral remote sensing image analysis has always been a challenging task and hence there are several techniques employed for exploring the images. Recent approaches include visualizing hyperspectral images as third order tensors and processing using various tensor decomposition methods. This paper focuses on behavioural analysis of hyperspectral images processed with various decompositions. The experiments includes processing raw hyperspectral image and pre-processed hyperspectral image with tensor decomposition methods such as, Multilinear Singular Value Decomposition and Low Multilinear Rank Approximation technique. The results are projected based on relative reconstruction error, classification and pixel reflectance spectrums. The analysis provides correlated experimental results, which emphasizes the need of pre-processing for hyperspectral images and the trend followed by the tensor decomposition methods.
关键词： Low Multilinear Rank Approximation,Remote sensing image,Pixel reflectance spectrums,Multilinear Singular Value Decomposition,Relative reconstruction error,Tensor decomposition
更新于2025-09-19 17:15:36
-
A low-rank estimation method for CTIS image reconstruction
摘要： The computed tomography image spectrometer (CTIS) is a snapshot hyperspectral imaging technique, which enables hyperspectral image acquisition in a dynamic scene. However, traditional image reconstruction methods with no explicit constraints will introduce high-frequency noise. The low-rank property has been used in hyperspectral image denoising and achieved great effects. We develop an effective method of low-rank estimation (LRE) for CTIS image reconstruction, which shows significant improvements in both the image quality and the spectral quality of the reconstructed image. Compared with the traditional methods, the peak signal-to-noise ratio of the LRE hyperspectral image can be increased by 8 dB, and the spectral-angular mapping can be decreased by 4 times.
关键词： computed tomography image spectrometers,image reconstruction,low-rank estimation,hyperspectral image
更新于2025-09-19 17:15:36
-
Error estimation of 3D reconstruction in 3D digital image correlation
摘要： Three-dimensional digital image correlation (3D-DIC) is widely used in various measurement fields. Once a DIC setup is established, different parameters, such as lens focal length, pixel size, stereo angle, and working distance, are easy to know or measure; the range of the matching error is generally 0.01–0.02 pixels. It would be very convenient if the measurement error could be estimated based on the parameters above without performing the entire DIC calculation process. In this study, a numerical simulation was conducted to study the variation of the 3D reconstruction error with the stereo angle in different measurement areas. It was found that the error of the center point was closely related to the error of the full field. Therefore, using simple parameters to describe the 3D reconstruction error of the center point is of great significance for estimating the overall error of a DIC system. The general solution of the 3D reconstruction equation was simplified on the premise that high order terms of pixel coordinates could be omitted. The derived error estimation formulas had a simple form and described the 3D reconstruction error of the center point in three directions. Through a set of static experiments, the 3D reconstruction error of a planar object under different stereo angles (from 10° to 120°) was studied. The matching error was calculated by a 2D-DIC software and inserted into the proposed formulas to obtain the estimated error. The estimated error was compared with the results of a 3D-DIC software, and the effectiveness of the proposed method was verified.
关键词： digital image correlation,error estimation,3D reconstruction
更新于2025-09-19 17:15:36
-
Optimal planar X-ray imaging soft tissue segmentation using a photon counting detector
摘要： A rigorous method for automated soft tissue segmentation using planar kilovoltage (kV) imaging, a photon counting detector (PCD), and a convolutional neural network is presented. The goal of the project was to determine the optimum number of energy bins in a PCD for soft tissue segmentation. Planar kV X-ray images of solid water (SW) phantoms with varying depth of cartilage were generated with a cone-beam analytical method and parallel-beam Monte Carlo simulations. Simulations were preformed using 2 to 5 PCD energy bins with equal photon fluence distribution. Simulated image signal to noise ratio (SNR) was varied between 10 to 250 measured after transmission through 4 cm of SW. Algorithms using non-linear as well as linear regression were used to predict the amount of cartilage for every pixel of the phantom. These algorithms were evaluated based on the mean squared error (MSE) between their prediction and the ground truth. The best algorithm was used to decompose randomly generated SW and cartilage images with an SNR of 100. These randomly generated images trained a U-Net convolutional neural network to segment the cartilage in the image. The results indicated the smallest MSE occurred for non-linear regression with 4 energy bins over all SNR. The trained U-Net was able to correctly segment all regions of cartilage for the smallest amount of cartilage used (4 mm) and segmented the region with > 99% categorical accuracy by pixel.
关键词： X-ray radiography and digital radiography (DR),Medical-image reconstruction methods and algorithms,computer-aided diagnosis
更新于2025-09-19 17:15:36
-
[IEEE 2018 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting - Boston, MA, USA (2018.7.8-2018.7.13)] 2018 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting - Millimeter-Wave Synthetic Aperture Focusing for Packaging Inspection System
摘要： Synthetic aperture focusing technique is proposed for developing a packaging inspection system. The SAF algorithm is reformulated. The SAF reformulation is tested for a package inspection application with finite element simulation data.
关键词： synthetic aperture radar,Synthetic aperture focusing,and inspection,sectional imaging,image reconstruction,Fourier optics
更新于2025-09-19 17:15:36
-
Prototype of an array SiPM-based scintillator Compton camera for radioactive materials detection
摘要： Purpose The Compton camera, which visualizes the distribution of gamma-ray sources based on the kinematics of Compton scattering, has advantage of wide field of view, broad range of energy and compact structure. Methods In this study, we proposed a prototype of Compton camera, which included array silicon photomultiplier (SiPM)-based position-sensitive detectors, data acquisition (DAQ) system and image reconstruction system. The detectors were composed of Ce-doped Gd3Al2Ga3O12 scintillator arrays and pixel Si-PM arrays. In DAQ system, symmetric charge division circuit, impedance bridge circuit and the delay coincidence algorithm were designed to record coincidence events. Simple back-projection algorithm and list-mode maximum likelihood expectation maximization algorithm were adopted for image reconstruction. The coordinate of longitude and latitude was used for image fusion. Results The performance of this Compton camera prototype system was evaluated. The results indicated that this system was able to locate a 137Cs point source within 20 s with the corresponding radiation dose of ~ 1.0 μSv/h. The angular resolution of point source was ~ 7° (FWHM), and the total energy resolution of 662 keV was 7.2%. Furthermore, we succeeded in separating two point sources of different energy [22Na (511 keV), 137Cs (662 keV)] in laboratory test. Conclusions This prototype of scintillator Compton camera offers capabilities for applications like source term investigation and radioactive materials detection.
关键词： Scintillator Compton camera,Image reconstruction,Compton imaging,Silicon photomultipliers
更新于2025-09-19 17:15:36
-
[IEEE 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) - Orlando, FL, USA (2018.12.17-2018.12.20)] 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) - GAN-Based Super Resolution for Accurate 3D Surface Reconstruction from Light Field Skin Images Towards Haptic Palpation
摘要： The development of vision technology for observation of skin surface and diagnosis of skin disease for preventing secondary infections caused by direct skin touch has consistently been in the medical field spotlight. Many studies have been conducted to acquire three dimensional (3D) data through stereo images, multiple images, and lasers because (3D) data of in-vivo skin image is essential for accurate medical diagnosis. However, stereo vision systems or 3D laser systems for obtaining 3D information require high cost and have high computational complexity, and hence they have not been used universally. Additionally, the use of such systems is still not preferred in the medical field due to limitations on visual decision making. Therefore, a haptic diagnosis system that can blend vision information from a camera and palpation information from a dermatologist has been considered. In this study, we propose a 3D skin surface reconstruction method using a light field camera for haptic rendering and palpation. To achieve this goal, we addressed the low resolution problem, which has been consistently present in light field cameras, through the generative adversarial nets (GANs)-based super resolution method, and exploited the light field system which has been applied only to the object scene for obtaining 3D skin surface texture. Experimental results show that the method proposed in this study is promising and offers sufficient potential for haptic diagnosis.
关键词： Light field images,deep learning,3D skin surface reconstruction,disparity map,haptic palpation,super resolution
更新于2025-09-19 17:15:36
-
Quantifying 3D structure and occlusion in dense tropical and temperate forests using close-range LiDAR
摘要： Terrestrial laser scanning (TLS) has emerged as a reference for three-dimensional measurements of forest structure as well as forest reconstruction and modeling. Ground-based measurements can be complemented by new light-weight sensors on unmanned aerial vehicles (UAVs) or laser scans from canopy cranes or towers. However, it is still largely unknown how much of the forest canopy volume can be sampled and how occlusion is spatially distributed. We present an approach for highly detailed 3D structure measurements based on TLS on the ground and above canopy measurements from a canopy crane or UAV platform, and assess their spatial sampling in terms of occlusion. Comparing the application in a dense tropical and temperate forest, we demonstrate the ability to sample the complete canopy volume with < 2% occlusion at very high spatial resolution when combining ground and above canopy measurements. This is necessary for a full canopy reconstruction. Ground-based TLS can provide sufficient coverage when no sampling of leaves and branches at top of canopy is required, whereas UAV or tower-based measurements show considerable occlusion in the mid- and understory. We therefore recommend to perform above canopy measurements under leaf off conditions, in sparse forests, or as an addition to ground measurements if a full representation of the whole canopy is required at very high spatial resolution. The latter can pave the way for studies on light availability, micrometeorology, sensor simulations and algorithm testing and development.
关键词： Remote sensing,Canopy architecture,Terrestrial laser scanning,Forest reconstruction,UAV
更新于2025-09-19 17:15:36
-
Effective orthoscopic integral imaging reconstruction via adjustable depth position
摘要： In this paper, we propose an effective orthoscopic three-dimensional reconstruction via adjustable depth position in integral imaging system. Compared to conventional integral imaging reconstruction method, the proposed method can directly reconstruct orthoscopic 3D images through one-step ray tracing with adjustable depth positions. Thus, a real, undistorted, orthoscopic three-dimensional images can be reconstructed various distances without the magnification and overlap process of conventional integral imaging reconstruction. To show the feasibility of the proposed method, the preliminary experiments are carried out and the some experimental results are presented.
关键词： Adjustable depth position,Orthoscopic integral imaging reconstruction,Integral imaging
更新于2025-09-19 17:15:36
-
[ACM Press the 16th ACM SIGGRAPH International Conference - Tokyo, Japan (2018.12.02-2018.12.03)] Proceedings of the 16th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry - VRCAI '18 - Projection mapping based on BRDF reconstruction from single RGBD image
摘要： There have been many researches on projection mapping focused on target objects tracking, geometric shape recovering or virtual materials simulating such as clothes. However, few people pay attention to the material of target object which actually influences the visual results of projection. We present a new projection mapping framework based on BRDF reconstruction for the goal of more real projection results by enhancing the effects of Augmented Reality. In the framework, 3D computer vision method is used to reconstruct the BRDF of target object with a single RGBD image. A new algorithm is proposed using two Convolutional Neural Networks(CNN) which can predict both normal map and reflectance map of the target surface simultaneously with the RGBD image. The predicted maps are used to render the content to be projected onto the target object. Our BRDF reconstruction algorithm can recover several materials in one scene correctly in use of just one image. Experimental results show our framework has impressive performance and relatively accurate consequence.
关键词： BRDF Reconstruction,Projection Mapping,Augmented Reality
更新于2025-09-19 17:15:36